dgx-spark-qwen38 / Machines / ASUS Ascent GX10
Local AI on the ASUS Ascent GX10
Also known as GX10, Ascent GX10. Sold with 128 GB, and with 64 GB since October 2026.
The ASUS Ascent GX10 is a GB10 machine: NVIDIA's Grace Blackwell chip and its unified memory, on DGX OS. One command turns it into a private AI server with OpenAI- and Anthropic-compatible APIs and a local cockpit, and no prompt, image or video leaves the box.
The reference box of the project: every measurement of the project was made on an ASUS Ascent GX10 with 128 GB, and a second GX10 was set up from scratch with the one command.
With 128 GB: every lane
| Lane | Measured |
|---|---|
| Qwen3.8-27B | 71.4 tok/s, greedy median, one request |
| Qwen3.8-Flash-Next 176B | 47.9 tok/s, on code, with FLASH_TIER=context |
| Flash FP4-Local | 55.4 tok/s, greedy median, at its default effort |
| Nemotron 3.5 Bolt | 140 tok/s, rewriting code, one request, reasoning off |
| Nemotron 3.5 Super VL | 69.5 tok/s, rewriting code, one request, reasoning off |
| Ornith 1.5 122B | 42.4 tok/s, greedy median, one request |
| Kolibri-1 | 48.0 tok/s, one request |
| Qwen-Image 2.1 | 7.5 s, with its Turbo, per 1024×1024 image |
| MiniMax-H3 | 126.2 to 127.9 s, with the Turbo adapter, for 4 s of 480P video |
With 64 GB: Bolt and the 27B
A 64 GB box serves NVIDIA's Nemotron 3.5 Bolt at 110.8 tok/s (greedy median) and keeps Qwen3.8-27B one Load away at 67.2 tok/s, both measured at a 64 GB budget on the reference box. Lanes that need 128 GB are refused before anything is downloaded. What runs on 64 GB, in detail.
Install it
On stock DGX OS, run this on the box. The same command updates it later.
curl -fsSL https://raw.githubusercontent.com/hasso5703/dgx-spark-qwen38/main/get.sh | bash- Numbers
- measured on an ASUS Ascent GX10 with 128 GB, methods in BENCHMARKS.md
- Maker's page
- ASUS Ascent GX10